Do intentional glosses on agent behavior track anything real inside models?
raphaelmilliere · x · 2026-09-01
Part of Raphael Millière's long thread on the METR/Redwood sabotage eval. He asks which intentional and anthropomorphic glosses (beliefs, goals) actually help interpret agent behavior, which are just storytelling metaphors, and whether such glosses track internal model mechanics—or whether that even matters. He notes Dwarkesh Patel was criticized for bolder metaphors like calling agent swarms "civilizations".
More from AGI Musings
- Duke Study of 4,439 People Finds Coworkers Quietly Rate AI Users as Lazier — aakashgupta · 2026-10-16
- DSPy Author's $70 O'Reilly Book Rejected by Engineer Who Now Just Tells Claude What to Do — lateinteraction · 2026-10-16
- 'A machine proving new math, a car driving up a wall': AI researcher on how weird it's getting — rand_longevity · 2026-10-16
- Yacine on training: 'Neural nets are lazy stupid idiots — I build hells to make them ubermensch' — yacineMTB · 2026-10-16
- Jeff Clune: Moving the Goalposts Will Be Humanity's Last Job — jeffclune · 2026-10-16
- Replit CEO Amjad Masad Says the Future of Work Is the 'Self-Driving Company' — TechCrunch AI · 2026-10-16